{"total":372,"rows":[{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212,"area":null},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"area":null},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160,"area":null},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"area":null},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"area":null},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87,"area":null},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"2504.15930","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","created":"2025-04-22","cited_by_count":61,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2309.02033","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","created":"2023-09-05","cited_by_count":52,"area":null},{"id":"2103.04850","title":"Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding","created":"2021-03-08","cited_by_count":50,"area":null},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2507.01663","title":"AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training","created":"2025-07-02","cited_by_count":41,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2110.14771","title":"ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets","created":"2021-10-27","cited_by_count":36,"area":null},{"id":"2402.14989","title":"Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data","created":"2024-02-22","cited_by_count":36,"area":null},{"id":"2406.12585","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","created":"2024-06-18","cited_by_count":33,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2111.02275","title":"Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25,"area":null},{"id":"2107.08861","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2503.20563","title":"TerraTorch: The Geospatial Foundation Models Toolkit","created":"2025-03-26","cited_by_count":25,"area":null},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25,"area":null},{"id":"2206.04122","title":"ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret","created":"2022-06-08","cited_by_count":24,"area":null},{"id":"2106.07551","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","created":"2021-06-05","cited_by_count":23,"area":null},{"id":"2210.03137","title":"Deep Inventory Management","created":"2022-10-06","cited_by_count":23,"area":null},{"id":"2310.07875","title":"TabLib: A Dataset of 627M Tables with Context","created":"2023-10-11","cited_by_count":23,"area":null},{"id":"2210.13708","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2301.01824","title":"Privacy and Efficiency of Communications in Federated Split Learning","created":"2023-01-04","cited_by_count":21,"area":null},{"id":"2405.02140","title":"An Information Theoretic Perspective on Conformal Prediction","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2107.01739","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","created":"2021-07-04","cited_by_count":20,"area":null},{"id":"2204.10022","title":"Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2510.19944","title":"Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2504.08784","title":"SLOs-Serve: Optimized Serving of Multi-SLO LLMs","created":"2025-04-05","cited_by_count":19,"area":null},{"id":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2106.00761","title":"Motif Prediction with Graph Neural Networks","created":"2021-05-26","cited_by_count":18,"area":null},{"id":"2201.01441","title":"Balsa: Learning a Query Optimizer Without Expert Demonstrations","created":"2022-01-05","cited_by_count":18,"area":null},{"id":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","cited_by_count":18,"area":null},{"id":"2101.11296","title":"FedH2L: Federated Learning with Model and Statistical Heterogeneity","created":"2021-01-27","cited_by_count":17,"area":null},{"id":"2208.08464","title":"CTRL: Clustering Training Losses for Label Error Detection","created":"2022-08-17","cited_by_count":17,"area":null},{"id":"2302.12862","title":"FLINT: A Platform for Federated Learning Integration","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2111.05969","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2312.05181","title":"Tenplex: Dynamic Parallelism for Deep Learning using Parallelizable Tensor Collections","created":"2023-12-08","cited_by_count":16,"area":null},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2110.15032","title":"OneFlow: Redesign the Distributed Deep Learning Framework from Scratch","created":"2021-10-28","cited_by_count":15,"area":null},{"id":"2106.04516","title":"Launchpad: A Programming Model for Distributed Machine Learning Research","created":"2021-06-07","cited_by_count":14,"area":null},{"id":"2210.00762","title":"Meta-Learning Priors for Safe Bayesian Optimization","created":"2022-10-03","cited_by_count":14,"area":null},{"id":"2209.10785","title":"Deep Lake: a Lakehouse for Deep Learning","created":"2022-09-22","cited_by_count":13,"area":null},{"id":"2408.00665","title":"AutoM3L: An Automated Multimodal Machine Learning Framework with Large Language Models","created":"2024-08-01","cited_by_count":13,"area":null},{"id":"2412.18293","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2504.03648","title":"AIBrix: Towards Scalable, Cost-Effective Large Language Model Inference Infrastructure","created":"2025-02-22","cited_by_count":13,"area":null},{"id":"2102.05447","title":"Searching for Alignment in Face Recognition","created":"2021-02-10","cited_by_count":12,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2205.04713","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","created":"2022-05-10","cited_by_count":12,"area":null},{"id":"2501.14755","title":"Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2602.18266","title":"A Probabilistic Framework for LLM-Based Model Discovery","created":"2026-02-20","cited_by_count":12,"area":null},{"id":"2305.15092","title":"FedZero: Leveraging Renewable Excess Energy in Federated Learning","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2408.00165","title":"Non-convolutional Graph Neural Networks","created":"2024-07-31","cited_by_count":11,"area":null},{"id":"2410.15625","title":"Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2603.19329","title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","created":"2026-03-18","cited_by_count":11,"area":null},{"id":"2110.02827","title":"Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2407.00125","title":"A Survey on Failure Analysis and Fault Injection in AI Systems","created":"2024-06-28","cited_by_count":10,"area":null},{"id":"2407.04168","title":"Learning Interpretable Differentiable Logic Networks","created":"2024-07-04","cited_by_count":10,"area":null},{"id":"2408.10672","title":"Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2502.21231","title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2204.06514","title":"Scalable Training of Language Models using JAX pjit and TPUv4","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2207.06339","title":"Learning robust marking policies for adaptive mesh refinement","created":"2022-07-13","cited_by_count":9,"area":null},{"id":"2302.12600","title":"EvoTorch: Scalable Evolutionary Computation in Python","created":"2023-02-24","cited_by_count":9,"area":null},{"id":"2305.18285","title":"Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity","created":"2023-05-29","cited_by_count":9,"area":null},{"id":"2311.03485","title":"CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2412.05218","title":"Transformers Meet Relational Databases","created":"2024-12-06","cited_by_count":9,"area":null},{"id":"2505.17745","title":"MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2601.17126","title":"EveNet: A Foundation Model for Particle Collision Data Analysis","created":"2026-01-23","cited_by_count":9,"area":null},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2107.04164","title":"Parallel and Multi-Objective Falsification with Scenic and VerifAI","created":"2021-07-09","cited_by_count":8,"area":null},{"id":"2107.08369","title":"Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning","created":"2021-07-18","cited_by_count":8,"area":null},{"id":"2303.06455","title":"Graph Neural Network contextual embedding for Deep Learning on Tabular Data","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2310.00109","title":"FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2311.10579","title":"Graph Neural Networks for Pressure Estimation in Water Distribution Systems","created":"2023-11-17","cited_by_count":8,"area":null},{"id":"2401.06786","title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2405.03911","title":"Federated Graph Condensation with Information Bottleneck Principles","created":"2024-05-07","cited_by_count":8,"area":null},{"id":"2410.16148","title":"PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters","created":"2024-10-21","cited_by_count":8,"area":null},{"id":"2604.28192","title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","created":"2026-04-30","cited_by_count":8,"area":null},{"id":"2106.12300","title":"Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning","created":"2021-06-23","cited_by_count":7,"area":null},{"id":"2310.04830","title":"Extract-Transform-Load for Video Streams","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2310.19685","title":"DGFN: Double Generative Flow Networks","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2403.04311","title":"Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2408.15992","title":"CoGen: Learning from Feedback with Coupled Comprehension and Generation","created":"2024-08-28","cited_by_count":7,"area":null}],"next_cursor":"100"}